Learn Anything — Guided Learning Coach

    1

    Turn your AI agent into a guided learning coach. Build a structured, resumable study repository with lessons, practice, progress tracking, and source-aware review. Supports English and Chinese.

    Free

    6 usesSecurity scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Learn Anything — Guided Learning Coach

    Example session with this skill installed

    I want to learn the basics of Rust programming. I have 1 hour a day for 14 days. I'm a beginner but I know some Python. Let's start a repository.

    • Read your context and instructions
    • Compiled the learn anything

    I initialized a learning repository for Rust programming and tailored the explanations to your Python background. The repository provides a structured place for your roadmap, daily lessons, exercises, source notes, and progress tracking.

    Start here

    Open START_HERE.md for the project guide and TODAY.md for today’s lesson. The roadmap is in 00_domain_map.md; your progress is recorded in progress.md.

    Day 1: Variables and immutability

    In Rust, variables are immutable by default: let x = 5; cannot be reassigned. Use let mut x = 5; when a value needs to change. Shadowing lets you bind a new value to the same name with another let, which is useful when transforming data while keeping each step clear.

    fn main() {
        let x = 5;
        let x = x + 1; // shadow x with a new value
        println!("{x}");
    }
    

    Practice

    1. Declare an immutable variable named x.
    2. Try to reassign it and read the compiler message.
    3. Use shadowing to give x a new value, then print it.

    Reply with your code or ask for the first concept explanation. After you complete the task, the skill can check your answer and update progress.md.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Traditional learning paths often lack structure, leaving you with a pile of unorganized bookmarks and half-finished tutorials. This skill transforms your AI agent into a dedicated learning engineer that builds a persistent, file-based learning repository. It moves beyond simple chat summaries to create a complete curriculum based on your specific goals and available materials.

    What it does

    • Scaffold repositories creates a multi-directory structure for notes, exercises, quizzes, and progress tracking.
    • Process materials extracts knowledge from user-provided PDFs, slide decks, Word docs, and webpage exports.
    • Generate knowledge maps builds dependency graphs, core concept lists, and 20-60-20 priority splits.
    • Execute daily cycles runs a structured "Explain, Demonstrate, Practice, Check, Reflect" teaching flow.
    • Diagnose errors analyzes mistakes using a specific taxonomy to identify conceptual gaps versus application failures.
    • Track progress maintains a strictly formatted progress.md file to log mastery ratings and weak points.

    How it works

    1. Intake where you define the domain, knowledge level, daily time budget, and provide source files.
    2. Scaffold command generates the local folder structure and initial README, TODAY, and START_HERE files.
    3. Map & Plan creates the core concept breakdown and a duration-based schedule with stage tests.
    4. Learn mode triggers daily sessions including a review, three concepts, a quiz, and a deliverable task.

    Frameworks & tools

    This skill is designed for agents with file I/O capabilities like Claude Code, Cursor, or Windsurf, but supports a fenced-block fallback for generic chat interfaces. It includes dedicated logic for handling English and Chinese locales.

    Why this beats prompting it yourself

    Standard prompts forget your progress and fail to organize knowledge hierarchically. This skill enforces a rigorous pedagogical framework, maintains a source-first reliability layer to prevent hallucinations, and creates a permanent assets folder you can reference long after the session ends.

    Use cases

    • Technical upskilling like mastering a new programming library by building a capstone project.
    • Exam preparation using structured stage tests and targeted remedial exercises for weak points.
    • Professional research synthesizing complex PDFs and slide decks into a grounded knowledge repository.
    • Non-technical hobbies creating beginner-friendly study plans with zero-code project alternatives.

    Known limitations

    Does not provide professional medical, legal, or financial advice. Requires manual verification of facts if web access is unavailable. Material processing depends on the agent's ability to read or OCR specific file formats.

    Educational use only. Not a substitute for professional advice in high-stakes domains. Material extraction requires the agent to have file-read access or user-provided text.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    6 uses

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 24 days ago

    • Free with an Agensi account

    Requires

    Git

    Permissions

    Terminal / Shell
    Read Files
    Write Files

    File access is needed to read the skill instructions/templates and learner-provided materials, and to create or update the learner’s study repository and progress files. Terminal access is used only when the agent runs the optional local scaffolding scripts. Network access is not required.

    Listed1 month ago
    Updated24 days ago

    What's inside

    Frequently Asked Questions

    Unlike one-off prompts, this skill creates a persistent, file-based repository (including a progress.md tracker) that preserves your learning context and avoids the 'memory fade' common in standard chat sessions.

    This skill is optimized for agents with file-system access like Claude Code, Cursor, or Windsurf; however, it includes a fallback mode that generates structured markdown blocks for copy-pasting into any standard chat interface.

    The free download includes the core skill instructions, learning templates, optional local scaffolding scripts, and guides for supported agent workflows. It uses the MIT License.

    Yes, the skill is designed to ingest and synthesize knowledge from your specific source materials, including PDFs, slide decks, and Word documents, to ensure the curriculum is grounded in your provided data.

    The skill uses a 20-60-20 priority split to focus on core concepts first, combined with a 'Diagnose' feature that categorizes your mistakes to identify whether you have a conceptual gap or just a practical application error.

    New in Education & Learning